A sudden extreme change in the weather can result in significant impact onthe life system in the present-day scenario. A well-planned prediction for damage during extreme weather conditions can have minimal impact on the grid components and efficient response and recovery models. With technology advancements and innovation in smart grid technologies we can now have accesses to uninterrupted power supply with smart utilization of energy and reduce CO2 emissions. Artificial Intelligence plays a vital role insolving present day power issues. Large amounts of data and rapid usage of computational power has accelerated to use machine learning models topredict and forecast the energy demand. Hence this study aims to determine how machine learning will improve the microgrid operation at Tezpur University. The main application areas studied in this thesis are identified as demand and load forecasting, simulating Photovoltaic (PV)production in a Microgrid and power outages. This thesis is aimed to develop and compare different ML algorithms to test validate and predict the PV production, energy demand and power outages.